import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')
from scipy.stats import zscore

Breast cancer

It is a disease in which cells in the breast grow out of control. There are different kinds of breast cancer. The kind of breast cancer depends on which cells in the breast turn into cancer.

Breast cancer can begin in different parts of the breast. A breast is made up of three main parts: lobules, ducts, and connective tissue. The lobules are the glands that produce milk. The ducts are tubes that carry milk to the nipple. The connective tissue (which consists of fibrous and fatty tissue) surrounds and holds everything together. Most breast cancers begin in the ducts or lobules.

Breast cancer can spread outside the breast through blood vessels and lymph vessels. When breast cancer spreads to other parts of the body, it is said to have metastasized.

df=pd.read_csv('BC.csv')
df

	mean_radius	mean_texture	mean_perimeter	mean_area	mean_smoothness	diagnosis
0	17.99	10.38	122.80	1001.0	0.11840	0
1	20.57	17.77	132.90	1326.0	0.08474	0
2	19.69	21.25	130.00	1203.0	0.10960	0
3	11.42	20.38	77.58	386.1	0.14250	0
4	20.29	14.34	135.10	1297.0	0.10030	0
...	...	...	...	...	...	...
564	21.56	22.39	142.00	1479.0	0.11100	0
565	20.13	28.25	131.20	1261.0	0.09780	0
566	16.60	28.08	108.30	858.1	0.08455	0
567	20.60	29.33	140.10	1265.0	0.11780	0
568	7.76	24.54	47.92	181.0	0.05263	1

569 rows × 6 columns

df.head()

	mean_radius	mean_texture	mean_perimeter	mean_area	mean_smoothness	diagnosis
0	17.99	10.38	122.80	1001.0	0.11840	0
1	20.57	17.77	132.90	1326.0	0.08474	0
2	19.69	21.25	130.00	1203.0	0.10960	0
3	11.42	20.38	77.58	386.1	0.14250	0
4	20.29	14.34	135.10	1297.0	0.10030	0

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 569 entries, 0 to 568
Data columns (total 6 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   mean_radius      569 non-null    float64
 1   mean_texture     569 non-null    float64
 2   mean_perimeter   569 non-null    float64
 3   mean_area        569 non-null    float64
 4   mean_smoothness  569 non-null    float64
 5   diagnosis        569 non-null    int64  
dtypes: float64(5), int64(1)
memory usage: 26.8 KB

df.describe()

	mean_radius	mean_texture	mean_perimeter	mean_area	mean_smoothness	diagnosis
count	569.000000	569.000000	569.000000	569.000000	569.000000	569.000000
mean	14.127292	19.289649	91.969033	654.889104	0.096360	0.627417
std	3.524049	4.301036	24.298981	351.914129	0.014064	0.483918
min	6.981000	9.710000	43.790000	143.500000	0.052630	0.000000
25%	11.700000	16.170000	75.170000	420.300000	0.086370	0.000000
50%	13.370000	18.840000	86.240000	551.100000	0.095870	1.000000
75%	15.780000	21.800000	104.100000	782.700000	0.105300	1.000000
max	28.110000	39.280000	188.500000	2501.000000	0.163400	1.000000

df.isnull().sum()

mean_radius        0
mean_texture       0
mean_perimeter     0
mean_area          0
mean_smoothness    0
diagnosis          0
dtype: int64

df.tail()

	mean_radius	mean_texture	mean_perimeter	mean_area	mean_smoothness	diagnosis
564	21.56	22.39	142.00	1479.0	0.11100	0
565	20.13	28.25	131.20	1261.0	0.09780	0
566	16.60	28.08	108.30	858.1	0.08455	0
567	20.60	29.33	140.10	1265.0	0.11780	0
568	7.76	24.54	47.92	181.0	0.05263	1

sns.pairplot(df,hue='diagnosis')

<seaborn.axisgrid.PairGrid at 0x135689fe850>

df['diagnosis'].value_counts().plot.pie(autopct="%.2f%%")

<AxesSubplot:ylabel='diagnosis'>

plt.figure(figsize=(14,6))
corr=df.corr(method='pearson')
heatmap=sns.heatmap(corr,annot=True,vmax=1,vmin=-1,linewidths=1,linecolor='White')
plt.show()

for i in df.columns:
    sns.distplot(df[i])
    plt.show()

for i in df.columns:
    sns.boxplot(df[i])
    plt.show()

import plotly.express as px
fig = px.scatter_3d(df, x='mean_texture', y='mean_radius', z='diagnosis',
              color='mean_area')
fig.show()

MACHINE LEARNING MODEL

from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score,classification_report

KNN

X=df.iloc[:,:-1]
y=df['diagnosis']

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.20,random_state=123)
print(X_train.shape,y_train.shape)
print(X_test.shape,y_test.shape)

(455, 5) (455,)
(114, 5) (114,)

se=StandardScaler()
X_train=se.fit_transform(X_train)
X_test=se.fit_transform(X_test)

kn=KNeighborsClassifier()
kn.fit(X_train,y_train)

KNeighborsClassifier()

y_train_pred=kn.predict(X_train)
y_test_pred=kn.predict(X_test)

print(accuracy_score(y_train,y_train_pred))
print(accuracy_score(y_test,y_test_pred))

0.9318681318681319
0.9122807017543859

LOGISTIC REGRESSION

from sklearn.linear_model import LogisticRegression

lr=LogisticRegression()
lr.fit(X_train,y_train)

LogisticRegression()

y_train_pred=lr.predict(X_train)
y_test_pred=lr.predict(X_test)

print(accuracy_score(y_train,y_train_pred))
print(accuracy_score(y_test,y_test_pred))

0.9296703296703297
0.9385964912280702

print(classification_report(y_train,y_train_pred))
print(classification_report(y_test,y_test_pred))

              precision    recall  f1-score   support

           0       0.93      0.88      0.90       171
           1       0.93      0.96      0.94       284

    accuracy                           0.93       455
   macro avg       0.93      0.92      0.92       455
weighted avg       0.93      0.93      0.93       455

              precision    recall  f1-score   support

           0       0.90      0.93      0.92        41
           1       0.96      0.95      0.95        73

    accuracy                           0.94       114
   macro avg       0.93      0.94      0.93       114
weighted avg       0.94      0.94      0.94       114

DECISION TREE

from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import plot_tree

dt=DecisionTreeClassifier()
dt.fit(X_train,y_train)

DecisionTreeClassifier()

y_train_pred=dt.predict(X_train)
y_test_pred=dt.predict(X_test)

print(classification_report(y_train,y_train_pred))
print(classification_report(y_test,y_test_pred))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00       171
           1       1.00      1.00      1.00       284

    accuracy                           1.00       455
   macro avg       1.00      1.00      1.00       455
weighted avg       1.00      1.00      1.00       455

              precision    recall  f1-score   support

           0       0.84      0.90      0.87        41
           1       0.94      0.90      0.92        73

    accuracy                           0.90       114
   macro avg       0.89      0.90      0.90       114
weighted avg       0.91      0.90      0.90       114

dt1=DecisionTreeClassifier(max_depth=6)
dt1.fit(X_train,y_train)

DecisionTreeClassifier(max_depth=6)

y_train_pred=dt1.predict(X_train)
y_test_pred=dt1.predict(X_test)

print(classification_report(y_train,y_train_pred))
print(classification_report(y_test,y_test_pred))

              precision    recall  f1-score   support

           0       0.98      0.99      0.99       171
           1       1.00      0.99      0.99       284

    accuracy                           0.99       455
   macro avg       0.99      0.99      0.99       455
weighted avg       0.99      0.99      0.99       455

              precision    recall  f1-score   support

           0       0.84      0.90      0.87        41
           1       0.94      0.90      0.92        73

    accuracy                           0.90       114
   macro avg       0.89      0.90      0.90       114
weighted avg       0.91      0.90      0.90       114

fig,ax=plt.subplots(figsize=(10,10))
chart=plot_tree(dt1,max_depth=6,feature_names=X.columns,filled=True,fontsize=10)